I am trying to run this implementation using a Google Colab environment on my local laptop, a remote server containing the GPUs I'm using for training, and a docker container on the server where the scripts are running. It's been smooth sailing until I attempt to run the SIBR Viewer after training. I get this output:
[SIBR] -- INFOS --: Initialization of GLFW
[SIBR] -- INFOS --: OpenGL Version: 4.5 (Compatibility Profile) Mesa 23.2.1-1ubuntu3.1~22.04.2[major: 4, minor: 5]
Number of input Images to read: 5822
Number of Cameras set up: 5822
[SIBR] -- INFOS --: Error: can't load mesh '/content/hierarchical-3d-gaussians/data/small_city/camera_calibration/aligned/sparse/0/points3d.txt.
[SIBR] -- INFOS --: Error: can't load mesh '/content/hierarchical-3d-gaussians/data/small_city/camera_calibration/aligned/sparse/0/points3d.ply.
[SIBR] -- INFOS --: Error: can't load mesh '/content/hierarchical-3d-gaussians/data/small_city/camera_calibration/aligned/sparse/0/points3d.obj.
LOADSFM: Try to open /content/hierarchical-3d-gaussians/data/small_city/camera_calibration/aligned/sparse/0/points3D.bin
Num 3D pts 2390040
[SIBR] -- INFOS --: SfM Mesh '/content/hierarchical-3d-gaussians/data/small_city/camera_calibration/aligned/sparse/0/points3d.txt successfully loaded. (2390040) vertices detected. Init GL ...
[SIBR] -- INFOS --: Init GL mesh complete
USED RES (1024,690) scene w h 1024 : 690 NAME pass1_0000.jpg
Warning: GLParameter user_color does not exist in shader PointBased
[SIBR] -- INFOS --: Allowing up to 18567281 Gaussians in VRAM
Using 12692718529 bytes for scene
[SIBR] -- INFOS --: Initializing Raycaster
Cameras ID inconsistent. Setting default interpolation path.
[SIBR] -- INFOS --: Interactive camera using (0.009,1100) near/far planes.
Warning: GLParameter user_color does not exist in shader points_shader
Switched to trackball mode.
images_path: /content/hierarchical-3d-gaussians/data/small_city/camera_calibration/rectified/images
Cameras ID inconsistent. Setting default interpolation path.
Segmentation fault (core dumped)
Tue Nov 19 00:55:13 2024
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.127.05 Driver Version: 550.127.05 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA A100-SXM4-80GB On | 00000000:07:00.0 Off | 0 |
| N/A 47C P0 109W / 400W | 671MiB / 81920MiB | 87% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 1 NVIDIA A100-SXM4-80GB On | 00000000:0F:00.0 Off | 0 |
| N/A 46C P0 198W / 400W | 671MiB / 81920MiB | 91% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 2 NVIDIA A100-SXM4-80GB On | 00000000:47:00.0 Off | 0 |
| N/A 45C P0 102W / 400W | 671MiB / 81920MiB | 78% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 3 NVIDIA A100-SXM4-80GB On | 00000000:4E:00.0 Off | 0 |
| N/A 45C P0 204W / 400W | 671MiB / 81920MiB | 79% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 4 NVIDIA A100-SXM4-80GB On | 00000000:87:00.0 Off | 0 |
| N/A 57C P0 224W / 400W | 675MiB / 81920MiB | 92% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 5 NVIDIA A100-SXM4-80GB On | 00000000:90:00.0 Off | 0 |
| N/A 57C P0 226W / 400W | 671MiB / 81920MiB | 92% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 6 NVIDIA A100-SXM4-80GB On | 00000000:B7:00.0 Off | 0 |
| N/A 61C P0 232W / 400W | 671MiB / 81920MiB | 79% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
| 7 NVIDIA A100-SXM4-80GB On | 00000000:BD:00.0 Off | 0 |
| N/A 58C P0 233W / 400W | 671MiB / 81920MiB | 78% Default |
| | | Disabled |
+-----------------------------------------+------------------------+----------------------+
+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+
I've used budget 6000 (and other values) too but that doesn't seem to change anything.
zhicong01
commented
4 days ago
I am trying to run this implementation using a Google Colab environment on my local laptop, a remote server containing the GPUs I'm using for training, and a docker container on the server where the scripts are running. It's been smooth sailing until I attempt to run the SIBR Viewer after training. I get this output:
I've used budget 6000 (and other values) too but that doesn't seem to change anything.